INDEX

Explanations

explicit mentions of something without directly naming it

oai_token-act-pair · gpt-3.5-turbo

words related to explicit or formal declarations and statements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 heart

-0.72

 throats

-0.68

Posts

-0.67

 Memories

-0.65

 Garry

-0.65

 favourites

-0.64

GER

-0.63

 vocabulary

-0.63

 jaws

-0.61

 enthus

-0.61

POSITIVE LOGITS

 addressed

0.99

 detonated

0.87

 contradicted

0.84

 challenged

0.81

 endorsed

0.79

 denounced

0.78

 defended

0.77

 declare

0.76

 testified

0.76

 preceded

0.75

Activations Density 0.049%

explicit mentions of something without directly naming it

words related to explicit or formal declarations and statements

No Comments

No Known Activations